Comparison of floating gate neural network memory cells in standard VLSI CMOS technology

Several floating gate MOSFET structures, for potential use as analog memory elements in neural networks, have been fabricated in a standard 2 mum double-polysilicon CMOS process. Their physical and programming characteristics are compared with each other and with similar structures reported in the literature. None of the circuits under consideration require special fabrication techniques. The criteria used to determine the structure most suitable for neural network memory applications include the symmetry of charging and discharging characteristics, programming voltage magnitudes, the area required, and the effectiveness of geometric field enhancement techniques. This work provides a layout for an analog neural network memory based on previously unexplored criteria and results. The authors have found that the best designs (a) use the poly1 to poly2 oxide for injection; (b) need not utilize ;field enhancement' techniques; (c) use poly1 to diffusion oxide for a coupling capacitor; and (d) size capacitor ratios to provide a wide range of possible programming voltages.

[1]  L.D. Jackel,et al.  Analog electronic neural network circuits , 1989, IEEE Circuits and Devices Magazine.

[2]  Chenming Calvin Hu,et al.  The EEPROM as an analog memory drive , 1989 .

[3]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[4]  W. Guggenbuhl,et al.  An analog trimming circuit based on a floating-gate device , 1988 .

[5]  D. Kerr,et al.  Evidence for surface asperity mechanism of conductivity in oxide grown on polycrystalline silicon , 1977 .

[6]  M. Lenzlinger,et al.  Fowler‐Nordheim Tunneling into Thermally Grown SiO2 , 1969 .

[7]  S.K. Lai,et al.  Flash memories: the best of two worlds , 1989, IEEE Spectrum.

[8]  F. Masuoka,et al.  Electrically alterable avalanche-injection-type MOS READ-ONLY memory with stacked-gate structure , 1976, IEEE Transactions on Electron Devices.

[9]  Bing J. Sheu,et al.  Analog floating-gate synapses for general-purpose VLSI neural computation , 1991 .

[10]  Y. Nissan-Cohen,et al.  A novel floating-gate method for measurement of ultra-low hole and electron gate currents in MOS transistors , 1986, IEEE Electron Device Letters.

[11]  L. Carley,et al.  Trimming analog circuits using floating-gate analog MOS memory , 1989, IEEE International Solid-State Circuits Conference, 1989 ISSCC. Digest of Technical Papers.

[12]  S. Tam,et al.  An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapses , 1990, International 1989 Joint Conference on Neural Networks.

[13]  Z. Weinberg,et al.  On tunneling in metal‐oxide‐silicon structures , 1982 .

[14]  Carver A. Mead,et al.  VLSI architectures for implementation of neural networks , 1987 .

[15]  Y. Takefuji,et al.  Analog components for the VLSI of neural networks , 1990, IEEE Circuits and Devices Magazine.

[16]  M.A. Brooke,et al.  A floating-gate MOSFET with tunneling injector fabricated using a standard double-polysilicon CMOS process , 1991, IEEE Electron Device Letters.

[17]  R. Ellis.  Fowler-Nordheim emission from non-planar surfaces , 1982, IEEE Electron Device Letters.

[18]  G. Yaron,et al.  A 16K E/SUP 2/PROM employing new array architecture and designed-in reliability features , 1982, IEEE Journal of Solid-State Circuits.

[19]  Mohammed Ismail,et al.  Neural Network Building Blocks for Analog MOS VLSI , 1993 .

[20]  H. Grubin.  The physics of semiconductor devices , 1979, IEEE Journal of Quantum Electronics.